Stars
Testing adaptation of the DINOv2/3 encoders for vision tasks with Low-Rank Adaptation (LoRA)
Fully Open Framework for Democratized Multimodal Training
VisioFirm: Cross-Platform AI-assisted Annotation Tool for Computer Vision
crnn chinese_plate_recognition
This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."
dualFisheye Stitching Demo( windows-desktop panorama viewer)
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
Official code for "No time to train! Training-Free Reference-Based Instance Segmentation"
这是一个简单的技术科普教程项目，主要聚焦于解释一些有趣的，前沿的技术概念和原理。每篇文章都力求在 5 分钟内阅读完成。
Fast and memory-efficient exact attention
Everything about the SmolLM and SmolVLM family of models
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)
A little word cloud generator in Python
Automatically crawl arXiv papers daily and summarize them using AI. Illustrating them using GitHub Pages.
Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.
Everything about note management. All in Zotero.
强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/
Zotero BabelDOC plugin, for Immersive Translate Pro members.
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
[NeurIPS 2025] Official code implementation of Perception R1: Pioneering Perception Policy with Reinforcement Learning
🚀 「大模型」1小时从0训练26M参数的视觉多模态VLM！🌏 Train a 26M-parameter VLM from scratch in just 1 hours!
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
A multi-modal, photo-realistic dataset for online end-to-end scene change detection and more (accepted to IROS2021).
Official repository of 'Visual-RFT: Visual Reinforcement Fine-Tuning' & 'Visual-ARFT: Visual Agentic Reinforcement Fine-Tuning'’
🍒 Cherry Studio is a desktop client that supports for multiple LLM providers.
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.